The platform for open and practice-oriented research

product

Deep learning to predict falls in older adults based on daily-life trunk accelerometry

PDF

product

Off the charts: A comparative analysis of data visualisations in online science news from South Africa and the USA

Terms like ‘big data’, ‘data science’, and ‘data visualisation’ have become buzzwords in recent years and are increasingly intertwined with journalism. Data visualisation may further blur the lines between science communication and graphic design. Our study is situated in these overlaps to compare the design of data visualisations in science news stories across four online news media platforms in South Africa and the United States. Our study contributes to an understanding of how well-considered data visualisations are tools for effective storytelling, and offers practical recommendations for using data visualisation in science communication efforts.

LINK

product

Long-Range Human Detection in Drone Camera Images

In recent years, drones have increasingly supported First Responders (FRs) in monitoring incidents and providing additional information. However, analysing drone footage is time-intensive and cognitively demanding. In this research, we investigate the use of AI models for the detection of humans in drone footage to aid FRs in tasks such as locating victims. Detecting small-scale objects, particularly humans from high altitudes, poses a challenge for AI systems. We present first steps of introducing and evaluating a series of YOLOv8 Convolutional Neural Networks (CNNs) for human detection from drone images. The models are fine-tuned on a created drone image dataset of the Dutch Fire Services and were able to achieve a 53.1% F1-Score, identifying 439 out of 825 humans in the test dataset. These preliminary findings, validated by an incident commander, highlight the promising utility of these models. Ongoing efforts aim to further refine the models and explore additional technologies.

MULTIFILE

Long-Range Human Detection in Drone Camera Images

product

DigiPig

The goal of this study was to develop an automated monitoring system for the detection of pigs’ bodies, heads and tails. The aim in the first part of the study was to recognize individual pigs (in lying and standing positions) in groups and their body parts (head/ears, and tail) by using machine learning algorithms (feature pyramid network). In the second part of the study, the goal was to improve the detection of tail posture (tail straight and curled) during activity (standing/moving around) by the use of neural network analysis (YOLOv4). Our dataset (n = 583 images, 7579 pig posture) was annotated in Labelbox from 2D video recordings of groups (n = 12–15) of weaned pigs. The model recognized each individual pig’s body with a precision of 96% related to threshold intersection over union (IoU), whilst the precision for tails was 77% and for heads this was 66%, thereby already achieving human-level precision. The precision of pig detection in groups was the highest, while head and tail detection precision were lower. As the first study was relatively time-consuming, in the second part of the study, we performed a YOLOv4 neural network analysis using 30 annotated images of our dataset for detecting straight and curled tails. With this model, we were able to recognize tail postures with a high level of precision (90%)

MULTIFILE

product

Deep Learning-Based Localization Approach for Autonomous Robots in the RobotAtFactory 4.0 Competition

Accurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.

PDF

product

Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning

Masonry structures represent the highest proportion of building stock worldwide. Currently, the structural condition of such structures is predominantly manually inspected which is a laborious, costly and subjective process. With developments in computer vision, there is an opportunity to use digital images to automate the visual inspection process. The aim of this study is to examine deep learning techniques for crack detection on images from masonry walls. A dataset with photos from masonry structures is produced containing complex backgrounds and various crack types and sizes. Different deep learning networks are considered and by leveraging the effect of transfer learning crack detection on masonry surfaces is performed on patch level with 95.3% accuracy and on pixel level with 79.6% F1 score. This is the first implementation of deep learning for pixel-level crack segmentation on masonry surfaces. Codes, data and networks relevant to the herein study are available in: github.com/dimitrisdais/crack_detection_CNN_masonry.

PDF

Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning

product

Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application

Industrial robot manipulators are widely used for repetitive applications that require high precision, like pick-and-place. In many cases, the movements of industrial robot manipulators are hard-coded or manually defined, and need to be adjusted if the objects being manipulated change position. To increase flexibility, an industrial robot should be able to adjust its configuration in order to grasp objects in variable/unknown positions. This can be achieved by off-the-shelf vision-based solutions, but most require prior knowledge about each object tobe manipulated. To address this issue, this work presents a ROS-based deep reinforcement learning solution to robotic grasping for a Collaborative Robot (Cobot) using a depth camera. The solution uses deep Q-learning to process the color and depth images and generate a greedy policy used to define the robot action. The Q-values are estimated using Convolutional Neural Network (CNN) based on pre-trained models for feature extraction. Experiments were carried out in a simulated environment to compare the performance of four different pre-trained CNNmodels (RexNext, MobileNet, MNASNet and DenseNet). Results showthat the best performance in our application was reached by MobileNet,with an average of 84 % accuracy after training in simulated environment.

PDF

Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application

product

The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography

Chest imaging plays a pivotal role in screening and monitoring patients, and various predictive artificial intelligence (AI) models have been developed in support of this. However, little is known about the effect of decreasing the radiation dose and, thus, image quality on AI performance. This study aims to design a low-dose simulation and evaluate the effect of this simulation on the performance of CNNs in plain chest radiography. Seven pathology labels and corresponding images from Medical Information Mart for Intensive Care datasets were used to train AI models at two spatial resolutions. These 14 models were tested using the original images, 50% and 75% low-dose simulations. We compared the area under the receiver operator characteristic (AUROC) of the original images and both simulations using DeLong testing. The average absolute change in AUROC related to simulated dose reduction for both resolutions was <0.005, and none exceeded a change of 0.014. Of the 28 test sets, 6 were significantly different. An assessment of predictions, performed through the splitting of the data by gender and patient positioning, showed a similar trend. The effect of simulated dose reductions on CNN performance, although significant in 6 of 28 cases, has minimal clinical impact. The effect of patient positioning exceeds that of dose reduction.

LINK

product

Channel State Information (CSI) analysis for Predictive Maintenance using Convolutional Neural Network (CNN)

Channel State Information (CSI) analysis for Predictive Maintenance using Convolutiona Neural Network (CNN).

MULTIFILE

Search results

Products 85

Deep learning to predict falls in older adults based on daily-life trunk accelerometry

Off the charts: A comparative analysis of data visualisations in online science news from South Africa and the USA

Long-Range Human Detection in Drone Camera Images

DigiPig

Deep Learning-Based Localization Approach for Autonomous Robots in the RobotAtFactory 4.0 Competition

Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning

Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application

The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography

Channel State Information (CSI) analysis for Predictive Maintenance using Convolutional Neural Network (CNN)

Navigate to

Categories

Filters

Products 85

Deep learning to predict falls in older adults based on daily-life trunk accelerometry

Off the charts: A comparative analysis of data visualisations in online science news from South Africa and the USA

Long-Range Human Detection in Drone Camera Images

DigiPig

Deep Learning-Based Localization Approach for Autonomous Robots in the RobotAtFactory 4.0 Competition

Automatic crack classification and segmentation on masonry surfaces using convolutional neural networks and transfer learning

Deep Reinforcement Learning Applied to a Robotic Pick-and-Place Application

The Effect of Simulated Dose Reduction on the Performance of Artificial Intelligence in Chest Radiography

Channel State Information (CSI) analysis for Predictive Maintenance using Convolutional Neural Network (CNN)